DeepTrendLab — Top 50 AI Sources, Research & News

Run Isaac 0.1 on Replicate

Isaac 0.1 is a lightweight, grounded vision-language model built for real-world perception.

Run FLUX.2 on Replicate

FLUX.2 brings professional-grade image generation and editing with unprecedented detail, multi-reference support, and enterprise efficiency.

AI, networks and Mechanical Turks

How far do LLMs give us a step change in how good a search and recommendation system can be? Do they let you build one without needing a vast user…

How to prompt Nano Banana Pro

Nano Banana Pro brings powerful new capabilities in image generation and editing. Here are the main prompt tricks you should know.

Retro Diffusion's pixel art models are now on Replicate

Generate game assets, sprites, tiles, and pixel art with Retro Diffusion's suite of carefully crafted models.

Replicate is joining Cloudflare

A Guide to Solveit Features

Large language models make it remarkably easy to generate code. Ask ChatGPT or Claude to build an application, and you’ll receive hundreds of lines of working code in seconds. But…

RL without TD learning

In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference…

Build to Last

Note from Jeremy: We’re teaching a course starting Nov 3rd on how to build towards software mastery and craftsmanship whilst leveraging AI effectively. Have a look at solve.it.com if you’re…

Extract text from documents and images with Datalab Marker and OCR

Turn whole documents into markdown or grab line-level polygons with two new models from Datalab.

The U.S. Public Wants Regulation (or Prohibition) of Expert‑Level and Superhuman AI

Three‑quarters of U.S. adults want strong regulations on AI development, preferring oversight akin to pharmaceuticals rather than industry "self‑regulation."

How to prompt Veo 3.1

Google's Veo 3.1 brings powerful new video generation capabilities including reference images, first/last frame control, and enhanced image-to-video. Here's everything you need to know.

Let’s Build the GPT Tokenizer: A Complete Guide to Tokenization in LLMs

18 months ago, Andrej Karpathy set a challenge : “Can you take my 2h13m tokenizer video and translate the video into the format of a book chapter”. We’ve done it,…

How to Solve it With Code course now available

tl/dr: This is a copy of a one-off email I sent to all fast.ai forum users, with a long-overdue update. I had planned to send this email a year ago…

Michael Kleinman reacts to breakthrough AI safety legislation

FLI celebrates a landmark moment for the AI safety movement and highlights its growing momentum

IBM's Granite 4.0 is now on Replicate

Which image editing model should I use?

Here is the ultimate comparison post on all the latest image editing models.

Introducing our new search API

Find the best models and collections with a single API call.

A guide to understanding AI as normal technology

And a big change for this newsletter

Torch compile caching for inference speed

Cache your compiled models for faster boot and inference times

What exactly does word2vec learn?

What exactly does word2vec learn, and how? Answering this question amounts to understanding representation learning in a minimal yet interesting language modeling task. Despite the fact that word2vec is a…

Which Agent Causes Task Failures and When?Researchers from PSU and Duke explores automated failure attribution of LLM Multi-Agent Systems

In recent years, LLM Multi-Agent systems have garnered widespread attention for their collaborative approach to solving complex problems. However, it's a common scenario for these systems to fail at a…

Announcing Replicate's remote MCP server

Use our MCP to discover, compare, and run models from apps like Claude, Cursor, and VS Code.

How to prompt Veo 3 with images

You'll be surprised what you can do with AI video now.